t5_cnn_daily_mail_abstractive_summarizer_v3
Browse files- README.md +10 -21
- events.out.tfevents.1712251811.e24c4cb9975b.34.5 +3 -0
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: t5-small
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
metrics:
|
| 7 |
-
- rouge
|
| 8 |
model-index:
|
| 9 |
- name: logs
|
| 10 |
results: []
|
|
@@ -17,11 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -51,20 +54,6 @@ The following hyperparameters were used during training:
|
|
| 51 |
- lr_scheduler_warmup_steps: 500
|
| 52 |
- num_epochs: 5
|
| 53 |
|
| 54 |
-
### Training results
|
| 55 |
-
|
| 56 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Gen Len |
|
| 57 |
-
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:-------:|
|
| 58 |
-
| 0.2861 | 0.56 | 200 | 0.2978 | 0.5964 | 0.3284 | 0.5453 | 82.8793 |
|
| 59 |
-
| 0.2889 | 1.11 | 400 | 0.2988 | 0.5954 | 0.3284 | 0.5442 | 82.8793 |
|
| 60 |
-
| 0.2936 | 1.67 | 600 | 0.2988 | 0.5947 | 0.327 | 0.5432 | 82.8793 |
|
| 61 |
-
| 0.2743 | 2.23 | 800 | 0.2993 | 0.5946 | 0.3277 | 0.5442 | 82.8793 |
|
| 62 |
-
| 0.271 | 2.79 | 1000 | 0.2987 | 0.5942 | 0.3279 | 0.5442 | 82.8793 |
|
| 63 |
-
| 0.2742 | 3.34 | 1200 | 0.2992 | 0.5937 | 0.3274 | 0.5436 | 82.8793 |
|
| 64 |
-
| 0.2795 | 3.9 | 1400 | 0.2988 | 0.5934 | 0.327 | 0.543 | 82.8793 |
|
| 65 |
-
| 0.2696 | 4.46 | 1600 | 0.2989 | 0.5939 | 0.3276 | 0.5432 | 82.8793 |
|
| 66 |
-
|
| 67 |
-
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- Transformers 4.38.2
|
|
|
|
| 3 |
base_model: t5-small
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: logs
|
| 8 |
results: []
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 0.3006
|
| 19 |
+
- eval_rouge1: 0.5924
|
| 20 |
+
- eval_rouge2: 0.326
|
| 21 |
+
- eval_rougeL: 0.5425
|
| 22 |
+
- eval_gen_len: 82.8793
|
| 23 |
+
- eval_runtime: 174.5683
|
| 24 |
+
- eval_samples_per_second: 6.124
|
| 25 |
+
- eval_steps_per_second: 0.768
|
| 26 |
+
- epoch: 2.79
|
| 27 |
+
- step: 1000
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 54 |
- lr_scheduler_warmup_steps: 500
|
| 55 |
- num_epochs: 5
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.38.2
|
events.out.tfevents.1712251811.e24c4cb9975b.34.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26cd299440fe951f7f720917c06f4f1904b1aaa55c534e2cba46295f737572e2
|
| 3 |
+
size 28809
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242041896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3cff096dc67f56616ce1eebf7c117833d9b47832ae8995ea64ccffdca26cfa2
|
| 3 |
size 242041896
|